• 대한음성학회지:말소리
• /
• 제68권
• /
• pp.49-63
• /
• 2008

This paper describes the development and assessment of a hidden Markov model (HMM) based Tagalog speech synthesis system, where Tagalog is the most widely spoken indigenous language of the Philippines. Several aspects of the design process are discussed here. In order to build the synthesizer a speech database is recorded and phonetically segmented. The constructed speech corpus contains approximately 89 minutes of Tagalog speech organized in 596 spoken utterances. Furthermore, contextual information is determined. The quality of the synthesized speech is assessed by subjective tests employing 25 native Tagalog speakers as respondents. Experimental results show that the new system is able to obtain a 3.29 MOS which indicates that the developed system is able to produce highly intelligible neutral Tagalog speech with stable quality even when a small amount of speech data is used for HMM training.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.127-130
• /
• 2003

This paper describes an efficient method for unsupervised speaker adaptation. This method is based on selecting a subset of speakers who are acoustically close to a test speaker, and calculating adapted model parameters according to the previously stored sufficient HMM statistics of the selected speakers' data. In this method, only a few unsupervised test speaker's data are required for the adaptation. Also, by using the sufficient HMM statistics of the selected speakers' data, a quick adaptation can be done. Compared with a pre-clustering method, the proposed method can obtain a more optimal speaker cluster because the clustering result is determined according to test speaker's data on-line. Experiment results show that the proposed method attains better improvement than MLLR from the speaker independent model. Moreover the proposed method utilizes only one unsupervised sentence utterance, while MLLR usually utilizes more than ten supervised sentence utterances.

• 대한음성학회지:말소리
• /
• 제62호
• /
• pp.97-112
• /
• 2007

The speech recognizer in general operates in noisy acoustical environments. Many research works have been done to cope with the acoustical variations. Among them, the multiple-HMM model approach seems to be quite effective compared with the conventional methods. In this paper, we consider a multiple-model approach combined with the model compensation method and investigate the necessary number of the HMM model sets through noisy speech recognition experiments. By using the data-driven Jacobian adaptation for the model compensation, the multiple-model approach with only a few model sets for each noise type could achieve comparable results with the re-training method.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.217-220
• /
• 2007

This study outlines a small-sized dialog style ETRI Korean TTS system which applies a HMM based speech synthesis techniques. In order to build the VoiceFont, dialog-style 500 sentences were used in training HMM. And the context information about phonemes, syllables, words, phrases and sentence were extracted fully automatically to build context-dependent HMM. In training the acoustic model, acoustic features such as Mel-cepstrums, logF0 and its delta, delta-delta were used. The size of the VoiceFont which was built through the training is 0.93Mb. The developed HMM-based TTS system were installed on the ARM720T processor which operates 60MHz clocks/second. To reduce computation time, the MLSA inverse filtering module is implemented with Assembly language. The speed of the fully implemented system is the 1.73 times faster than real time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.391-394
• /
• 2004

This paper focuses on the DSP implementation of an HMM-based speech recognizer that can handle several hundred words of vocabulary size as well as speaker independency. First, we develop an HMM-based speech recognition system on the PC that operates on the frame basis with parallel processing of feature extraction and Viterbi decoding to make the processing delay as small as possible. Many techniques such as linear discriminant analysis, state-based Gaussian selection, and phonetic tied mixture model are employed for reduction of computational burden and memory size. The system is then properly optimized and compiled on the TMS320C6711 DSP for real-time operation. The implemented system uses 486kbytes of memory for data and acoustic models, and 24.5kbytes for program code. Maximum required time of 29.2ms for processing a frame of 32ms of speech validates real-time operation of the implemented system.

• 한국음향학회지
• /
• 제23권1호
• /
• pp.75-81
• /
• 2004

가우시안 선택기법은 연속 확률분포를 갖는 HMM음성인식기에서 인식성능을 저하시키지 않으면서 관측확률을 구할 때 계산되는 가우시안의 수를 줄여 효율적인 디코딩을 하기 위해 많이 이용되는 방법이다. 본 논문에서는 PTM 구조를 갖는 HMM에서 관측확률을 계산하는데 필요한 가우시안 함수의 부분집합을 구하는 새로운 가우시안 선택기법을 제안한다. PTM 모델에서는 음성신호의 음향특성에 따라 구분되는 클래스별 가중치와 공통적인 가우시안 집합을 이용하여 각 상태를 나타내는데, 제안한 방법에서는 PTM 구조가 갖는 이러한 특성을 이용하여 인식성능의 저하없이 관측확률 계산에 소요되는 적은 수의 가우시안 부분집합을 구한다. 실험결과 기존의 가우시안 선택기법이 가우시안 선택기법을 적용하지 않았을 경우에 비해 20∼30% 계산량을 필요로 하는데, 제안한 기법은 16.41%의 가우시안 함수 계산만으로도 별다른 인식성능 저하없이 인식 과정을 수행할 수 있었다.

• 한국음향학회지
• /
• 제23권2호
• /
• pp.173-179
• /
• 2004

음소 질의어 집합은 문맥 속에서 비슷한 조음 효과를 보이는 음소들을 분류해 놓은 것으로서, 음성 인식 시스템 학습 시 결정트리를 기반으로 HMM (hidden Markov model)의 상태들을 클러스터링할 때 사용된다. 현재까지의 음소 질의어 집합은 대부분 음성학자나 언어학자들에 의해 수작업으로 제시되어 왔는데, 이러한 지식 기반음소 질의어들은 언어 또는 유사음소 단위 (PLU: phone like unit)에 종속될 뿐 아니라 생성된 클러스터 내의 동질성을 저하시킬 수 있다는 단점이 있다. 본 논문에서는 이와 같은 문제점들을 해결하기 위해 음성 데이터를 사용하여 측정한 음소들 사이의 유사도를 기반으로 언어나 유사음소단위에 상관없이 자동으로 음소 질의어 집합을 생성하는 알고리즘을 제안한다. 실험결과, 제안한 방법으로 생성된 음소 질의어들을 사용한 인식기의 에러율이 약 14.3%감소하여 데이터 기반의 음소 질의어 집합이 상태 클러스터링에 효율적임을 관측하였다.

• 대한음성학회지:말소리
• /
• 제62호
• /
• pp.85-96
• /
• 2007

In this paper, we carried out recognition experiments for noisy speech having various levels of car noise and output of an audio system using the speech interface. The speech interface consists of three parts: pre-processing, acoustic echo canceller, post-processing. First, a high pass filter is employed as a pre-processing part to remove some engine noises. Then, an echo canceller implemented by using an FIR-type filter with an NLMS adaptive algorithm is used to remove the music or speech coming from the audio system in a car. As a last part, the MMSE-STSA based speech enhancement method is applied to the out of the echo canceller to remove the residual noise further. For recognition experiments, we generated test signals by adding music to the car noisy speech from Aurora 2 database. The HTK-based continuous HMM system is constructed for a recognition system. Experimental results show that the proposed speech interface is very promising for robust speech recognition in a noisy car environment.

• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.153-164
• /
• 2006

The MMSE-STSA based speech enhancement algorithm is widely used as a preprocessing for noise robust speech recognition. It weighs the gain of each spectral bin of the noisy speech using the estimate of noise and signal power spectrum. In this paper, we investigate the influence of parameters used to estimate the speech signal and noise power in MMSE-STSA upon the recognition performance of noisy speech. For experiments, we use the Aurora2 DB which contains noisy speech with subway, babble, car, and exhibition noises. The HTK-based continuous HMM system is constructed for recognition experiments. Experimental results are presented and discussed with our findings.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.435-447
• /
• 1996

In this paper, we propose the method that extracts the speech feature using the hearing model through signal processing techniques. The proposed method includes the following procedure ; normalization of the short-time speech block by its maximum value, multi-resolution analysis using the discrete wavelet transformation and re-synthesize using the discrete inverse wavelet transformation, differentiation after analysis and synthesis, full wave rectification and integration. In order to verify the performance of the proposed speech feature in the speech recognition task, korean digit recognition experiments were carried out using both the DTW and the VQ-HMM. The results showed that, in the case of using DTW, the recognition rates were 99.79% and 90.33% for speaker-dependent and speaker-independent task respectively and, in the case of using VQ-HMM, the rate were 96.5% and 81.5% respectively. And it indicates that the proposed speech feature has the potential for use as a simple and efficient feature for recognition task